© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 4133
    Prev
    Next
    INDEX
    Explanations

    headings with specific formatting or structure in the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <h3>
    -0.88
    madol
    -0.87
     Padilla
    -0.82
     Gentry
    -0.77
    ε
    -0.77
     Mali
    -0.74
    lblNewLabel
    -0.71
     Zamora
    -0.71
     Silvio
    -0.71
    LoginActivity
    -0.70
    POSITIVE LOGITS
    theless
    1.18
    <h4>
    1.08
     anúncio
    0.92
     Berna
    0.88
    UserScript
    0.87
    ed
    0.87
    strptime
    0.85
     @"/
    0.82
    ductory
    0.78
     دیکھیے
    0.78
    Activations Density 0.051%

    No Known Activations